Dismiss
InnovationQ will be updated on Sunday, Oct. 22, from 10am ET - noon. You may experience brief service interruptions during that time.
Browse Prior Art Database

Data Handling for Failed Hard Disk Drive in Redundant Array of Inexpensive Disks Subsystem

IP.com Disclosure Number: IPCOM000118493D
Original Publication Date: 1997-Feb-01
Included in the Prior Art Database: 2005-Apr-01
Document File: 4 page(s) / 114K

Publishing Venue

IBM

Related People

Iwasa, H: AUTHOR [+3]

Abstract

Disclosed is a method for data handling of the Redundant Array of Inexpensive Disks (RAID) subsystem to recover the data as much as possible and efficiently when more than two Hard Disk Drives (HDDs) failed to read/write data in the RAID subsystem.

This text was extracted from an ASCII text file.
This is the abbreviated version, containing approximately 54% of the total text.

Data Handling for Failed Hard Disk Drive in Redundant Array of Inexpensive
Disks Subsystem

      Disclosed is a method for data handling of the Redundant Array
of Inexpensive Disks (RAID) subsystem to recover the data as much as
possible and efficiently when more than two Hard Disk Drives (HDDs)
failed to read/write data in the RAID subsystem.

      The RAID controller in the RAID subsystem receives a command
from a host and calculates the Logical Block Address (LBA) where the
target data is stored and sends the command to the HDD(s) assembled
in the RAID subsystem.  The HDDs receive the command from the RAID
controller and read/write data from/to their medium.  When HDD-a, one
of the HDDs assembled in the RAID subsystem, failed to read/write
data from/to their medium at LBA=a in HDD-a, HDD-a is in error
condition and returns error status to the RAID controller.  The RAID
controller stops accessing to HDD-a.  But the RAID subsystem can
respond to the host system because the RAID subsystem can generate
the same data as HDD-a by using parity data (stored in one of HDDs
except HDD-a) which had been generated before HDD-a failed.  Thus,
the RAID subsystem can work even if one HDD failed.  This function
mode is named Degraded mode.  But if another HDD also entered in
error condition in Degraded mode, the RAID subsystem cannot work as
it does not have any more parity data.

      The following method can recover the data even if more than two
HDDs are in error...